{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:L3WNVL6DGIFM4EKI6INSCLE63R","short_pith_number":"pith:L3WNVL6D","canonical_record":{"source":{"id":"1712.08841","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-23T21:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"37399f0e58d7de62942009e8e8d75687fae952fc3c09ea8b40f450cea9e9ede3","abstract_canon_sha256":"3f2c8a7246487c0d8a780f4921e879b0c931b1f17cf480508a7cef1ced9f7aec"},"schema_version":"1.0"},"canonical_sha256":"5eecdaafc3320ace1148f21b212c9edc4f1265440d71219a2faffaf6102a6e27","source":{"kind":"arxiv","id":"1712.08841","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.08841","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"1712.08841v2","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08841","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"L3WNVL6DGIFM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L3WNVL6DGIFM4EKI","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L3WNVL6D","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:L3WNVL6DGIFM4EKI6INSCLE63R","target":"record","payload":{"canonical_record":{"source":{"id":"1712.08841","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-23T21:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"37399f0e58d7de62942009e8e8d75687fae952fc3c09ea8b40f450cea9e9ede3","abstract_canon_sha256":"3f2c8a7246487c0d8a780f4921e879b0c931b1f17cf480508a7cef1ced9f7aec"},"schema_version":"1.0"},"canonical_sha256":"5eecdaafc3320ace1148f21b212c9edc4f1265440d71219a2faffaf6102a6e27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:43.147785Z","signature_b64":"yu6ITUyAY8YG+Fh7AfeyN52Rsg1FSbUwrQfRXbmieXV48zOEFpjPFA7Ox8EYa6dDvzoHgUBLdk5YKV6LxbZmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eecdaafc3320ace1148f21b212c9edc4f1265440d71219a2faffaf6102a6e27","last_reissued_at":"2026-05-18T00:26:43.147259Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:43.147259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.08841","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+Wr20SkJ0AlOeXs72tRm59rJhwobeMVPwIS19wSI6JmMU7DIpBLX6kDKGYPN1hIpsSq6knhB8OWMctkfuQaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T03:46:14.389572Z"},"content_sha256":"6d405c5c3b44d65d0ddb041bd41b918dd47cc2889bce7cba577fb08ac05cedf1","schema_version":"1.0","event_id":"sha256:6d405c5c3b44d65d0ddb041bd41b918dd47cc2889bce7cba577fb08ac05cedf1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:L3WNVL6DGIFM4EKI6INSCLE63R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Long Short-Term Memory Networks for Sub-Character Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"George Townsend, Han He, Hua Yan, Lei Wu, Xiaokun Yang, Yi Feng, Zhimin Gao","submitted_at":"2017-12-23T21:12:23Z","abstract_excerpt":"Characters have commonly been regarded as the minimal processing unit in Natural Language Processing (NLP). But many non-latin languages have hieroglyphic writing systems, involving a big alphabet with thousands or millions of characters. Each character is composed of even smaller parts, which are often ignored by the previous work. In this paper, we propose a novel architecture employing two stacked Long Short-Term Memory Networks (LSTMs) to learn sub-character level representation and capture deeper level of semantic meanings. To build a concrete study and substantiate the efficiency of our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08841","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:26:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"necxG6rJ1xlfwZUptHfqHhVDFf2aA2kk4huwty9X0rBwkWBQJyjb9lL/3nywy2WxuMkF4YhOqzT1wUqxaHB1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T03:46:14.389921Z"},"content_sha256":"6417e5baa6f573d050acf10bafe06a0f95363b49b241288cd67870713679badc","schema_version":"1.0","event_id":"sha256:6417e5baa6f573d050acf10bafe06a0f95363b49b241288cd67870713679badc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3WNVL6DGIFM4EKI6INSCLE63R/bundle.json","state_url":"https://pith.science/pith/L3WNVL6DGIFM4EKI6INSCLE63R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3WNVL6DGIFM4EKI6INSCLE63R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T03:46:14Z","links":{"resolver":"https://pith.science/pith/L3WNVL6DGIFM4EKI6INSCLE63R","bundle":"https://pith.science/pith/L3WNVL6DGIFM4EKI6INSCLE63R/bundle.json","state":"https://pith.science/pith/L3WNVL6DGIFM4EKI6INSCLE63R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3WNVL6DGIFM4EKI6INSCLE63R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:L3WNVL6DGIFM4EKI6INSCLE63R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3f2c8a7246487c0d8a780f4921e879b0c931b1f17cf480508a7cef1ced9f7aec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-23T21:12:23Z","title_canon_sha256":"37399f0e58d7de62942009e8e8d75687fae952fc3c09ea8b40f450cea9e9ede3"},"schema_version":"1.0","source":{"id":"1712.08841","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.08841","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"1712.08841v2","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.08841","created_at":"2026-05-18T00:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"L3WNVL6DGIFM","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L3WNVL6DGIFM4EKI","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L3WNVL6D","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:6417e5baa6f573d050acf10bafe06a0f95363b49b241288cd67870713679badc","target":"graph","created_at":"2026-05-18T00:26:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Characters have commonly been regarded as the minimal processing unit in Natural Language Processing (NLP). But many non-latin languages have hieroglyphic writing systems, involving a big alphabet with thousands or millions of characters. Each character is composed of even smaller parts, which are often ignored by the previous work. In this paper, we propose a novel architecture employing two stacked Long Short-Term Memory Networks (LSTMs) to learn sub-character level representation and capture deeper level of semantic meanings. To build a concrete study and substantiate the efficiency of our ","authors_text":"George Townsend, Han He, Hua Yan, Lei Wu, Xiaokun Yang, Yi Feng, Zhimin Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-23T21:12:23Z","title":"Dual Long Short-Term Memory Networks for Sub-Character Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.08841","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6d405c5c3b44d65d0ddb041bd41b918dd47cc2889bce7cba577fb08ac05cedf1","target":"record","created_at":"2026-05-18T00:26:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3f2c8a7246487c0d8a780f4921e879b0c931b1f17cf480508a7cef1ced9f7aec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-12-23T21:12:23Z","title_canon_sha256":"37399f0e58d7de62942009e8e8d75687fae952fc3c09ea8b40f450cea9e9ede3"},"schema_version":"1.0","source":{"id":"1712.08841","kind":"arxiv","version":2}},"canonical_sha256":"5eecdaafc3320ace1148f21b212c9edc4f1265440d71219a2faffaf6102a6e27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eecdaafc3320ace1148f21b212c9edc4f1265440d71219a2faffaf6102a6e27","first_computed_at":"2026-05-18T00:26:43.147259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:43.147259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yu6ITUyAY8YG+Fh7AfeyN52Rsg1FSbUwrQfRXbmieXV48zOEFpjPFA7Ox8EYa6dDvzoHgUBLdk5YKV6LxbZmDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:43.147785Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.08841","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d405c5c3b44d65d0ddb041bd41b918dd47cc2889bce7cba577fb08ac05cedf1","sha256:6417e5baa6f573d050acf10bafe06a0f95363b49b241288cd67870713679badc"],"state_sha256":"918d9bddde4de23bb6f1cb7a109b1ae6665be4fde05935a7a68c4aedd2ec0b59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZnMwS7YGD+etbIaOc3dx4qn14Jeqn+9fop04QnylgszHP1bULfxY5a20K0zIGMQ4hTvEfr9pamYyfXuTHa5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T03:46:14.391813Z","bundle_sha256":"2051a4fabc094dfbe538f50ef7391202ef67f810186e9739f433cd4827b44e2a"}}